Jason T. Connor

The Platform Trial: An Efficient Strategy for Evaluating Multiple Treatments

The drug development enterprise is struggling. The development of new therapies is limited by high costs, slow progress, and a high failure rate, even in the late stages of development. Clinical trials are most commonly based on a “one population, one drug, one disease” strategy, in which the clinical trial infrastructure is created to test a single treatment in a homogeneous population. This approach has been largely unsuccessful for multiple diseases, including sepsis, dementia, and stroke. Despite promising preclinical and early human trials, there have been numerous negative phase 3 trials of treatments for Alzheimer disease1 and more than 40 negative phase 3 trials of neuroprotectants for stroke.2 Effective treatments for such diseases will likely require combining treatments to affect multiple targets in complex cellular pathways and, perhaps, tailoring treatments to subgroups defined by genetic, proteomic, metabolomic, or other markers.3 There has been increasing interest in efficient trial strategies designed to evaluate multiple treatments and combinations of treatments, in heterogeneous patient populations, with the capability to add new treatments in the future and eliminate investigational treatments lacking efficacy. The term “platform trial” is sometimes used to describe trials designed with these goals in mind, signifying the intent to build an experimental platform that will exist after the evaluation of any particular treatment.4 Currently, platform trials are enrolling patients or are under development in oncology, infectious diseases, neurology, and intensive care. Platform trials are an extension of adaptive trial design. An adaptive trial allows prespecified changes in key trial characteristics during the conduct of the trial in response to information accumulating during the trial; however, most adaptive trials focus on evaluating a single treatment in a single population. Examples of adaptive trials include traditional group-sequential trials, as well as trials incorporating reestimation of sample size or using variable randomization proportions (responseadaptive randomization).5 A platform trial is a type of adaptive trial designed to evaluate multiple treatments efficiently.

The established status epilepticus trial 2013.

Benzodiazepine‐refractory status epilepticus (established status epilepticus, ESE) is a relatively common emergency condition with several widely used treatments. There are no controlled, randomized, blinded clinical trials to compare the efficacy and tolerability of currently available treatments for ESE. The ESE treatment trial is designed to determine the most effective and/or the least effective treatment of ESE among patients older than 2 years by comparing three arms: fosphenytoin (fPHT) levetiracetam (LVT), and valproic acid (VPA). This is a multicenter, randomized, double‐blind, Bayesian adaptive, phase III comparative effectiveness trial. Up to 795 patients will be randomized initially 1:1:1, and response‐adaptive randomization will occur after 300 patients have been recruited. Randomization will be stratified by three age groups, 2–18, 19–65, and 66 and older. The primary outcome measure is cessation of clinical seizure activity and improving mental status, without serious adverse effects or further intervention at 60 min after administration of study drug. Each subject will be followed until discharge or 30 days from enrollment. This trial will include interim analyses for early success and futility. This trial will be considered a success if the probability that a treatment is the most effective is >0.975 or the probability that a treatment is the least effective is >0.975 for any treatment. Proposed total sample size is 795, which provides 90% power to identify the most effective and/or the least effective treatment when one treatment arm has a true response rate of 65% and the true response rate is 50% in the other two arms.

Percutaneous alternative to the Maze procedure for the treatment of persistent or long-standing persistent atrial fibrillation (aMAZE trial): Rationale and design

BACKGROUND Pulmonary vein antrum isolation (PVI) as a treatment of paroxysmal atrial fibrillation (AF) is associated with a high rate of success; however, outcomes for treating persistent and long-standing persistent AF with PVI alone are substantially lower and often require multiple procedures to maintain long-term freedom from atrial arrhythmias. Foci and/or substrate outside the pulmonary veins, particularly in the left atrial appendage (LAA), has been identified as a key mechanism in the maintenance of persistent AF and long-standing persistent AF. OBJECTIVE The goals of the study are to evaluate the safety and effectiveness of the LARIAT System to percutaneously isolate and ligate the LAA and to determine if LAA ligation as adjunctive therapy to PVI improves maintenance of sinus rhythm in patients with persistent and long-standing persistent AF. STUDY DESIGN The trial is a prospective, multicenter, randomized controlled study. The trial design incorporates a Bayesian adaptive design that will randomize a maximum of 600 patients with persistent or long-standing persistent AF to LAA ligation and PVI vs PVI alone in a 2:1 randomization. The primary end points include 30-day safety of the LARIAT procedure and freedom from documented AF, atrial flutter, or atrial tachycardia of more than 30 seconds at 12 months after the PVI off antiarrhythmic drugs. Key secondary outcomes include a composite of cardiovascular death and stroke, as well as quality of life. CONCLUSION The aMAZE trial will determine if LAA ligation as adjunctive therapy to PVI increases the efficacy of maintaining sinus rhythm in patients with persistent and long-standing persistent AF.

Bayesian adaptive trials offer advantages in comparative effectiveness trials: an example in status epilepticus.

OBJECTIVE We present a novel Bayesian adaptive comparative effectiveness trial comparing three treatments for status epilepticus that uses adaptive randomization with potential early stopping. STUDY DESIGN AND SETTING The trial will enroll 720 unique patients in emergency departments and uses a Bayesian adaptive design. RESULTS The trial design is compared to a trial without adaptive randomization and produces an efficient trial in which a higher proportion of patients are likely to be randomized to the most effective treatment arm while generally using fewer total patients and offers higher power than an analogous trial with fixed randomization when identifying a superior treatment. CONCLUSION When one treatment is superior to the other two, the trial design provides better patient care, higher power, and a lower expected sample size.

An overview of the adaptive designs accelerating promising trials into treatments (ADAPT-IT) project.

Randomized clinical trials, which aim to determine the efficacy and safety of drugs and medical devices, are a complex enterprise with myriad challenges, stakeholders, and traditions. Although the primary goal is scientific discovery, clinical trials must also fulfill regulatory, clinical, and ethical requirements. Innovations in clinical trials methodology have the potential to improve the quality of knowledge gained from trials, the protection of human subjects, and the efficiency of clinical research. Adaptive clinical trial methods represent a broad category of innovations intended to address a variety of long-standing challenges faced by investigators, such as sensitivity to previous assumptions and delayed identification of ineffective treatments. The implementation of adaptive clinical trial methods, however, requires greater planning and simulation compared with a more traditional design, along with more advanced administrative infrastructure for trial execution. The value of adaptive clinical trial methods in exploratory phase (phase 2) clinical research is generally well accepted, but the potential value and challenges of applying adaptive clinical trial methods in large confirmatory phase clinical trials are relatively unexplored, particularly in the academic setting. In the Adaptive Designs Accelerating Promising Trials Into Treatments (ADAPT-IT) project, a multidisciplinary team is studying how adaptive clinical trial methods could be implemented in planning actual confirmatory phase trials in an established, National Institutes of Health-funded clinical trials network. The overarching objectives of ADAPT-IT are to identify and quantitatively characterize the adaptive clinical trial methods of greatest potential value in confirmatory phase clinical trials and to elicit and understand the enthusiasms and concerns of key stakeholders that influence their willingness to try these innovative strategies.

The utility of Bayesian predictive probabilities for interim monitoring of clinical trials.

Background Bayesian predictive probabilities can be used for interim monitoring of clinical trials to estimate the probability of observing a statistically significant treatment effect if the trial were to continue to its predefined maximum sample size. Purpose We explore settings in which Bayesian predictive probabilities are advantageous for interim monitoring compared to Bayesian posterior probabilities, p-values, conditional power, or group sequential methods. Results For interim analyses that address prediction hypotheses, such as futility monitoring and efficacy monitoring with lagged outcomes, only predictive probabilities properly account for the amount of data remaining to be observed in a clinical trial and have the flexibility to incorporate additional information via auxiliary variables. Limitations Computational burdens limit the feasibility of predictive probabilities in many clinical trial settings. The specification of prior distributions brings additional challenges for regulatory approval. Conclusions The use of Bayesian predictive probabilities enables the choice of logical interim stopping rules that closely align with the clinical decision-making process.

The Stroke Hyperglycemia Insulin Network Effort (SHINE) trial: an adaptive trial design case study

BackgroundThe ‘Adaptive Designs Accelerating Promising Trials into Treatments (ADAPT-IT)’ project is a collaborative effort supported by the National Institutes of Health (NIH) and United States Food & Drug Administration (FDA) to explore how adaptive clinical trial design might improve the evaluation of drugs and medical devices. ADAPT-IT uses the National Institute of Neurologic Disorders & Stroke-supported Neurological Emergencies Treatment Trials (NETT) network as a ‘laboratory’ in which to study the development of adaptive clinical trial designs in the confirmatory setting. The Stroke Hyperglycemia Insulin Network Effort (SHINE) trial was selected for funding by the NIH-NINDS at the start of ADAPT-IT and is currently an ongoing phase III trial of tight glucose control in hyperglycemic acute ischemic stroke patients. Within ADAPT-IT, a Bayesian adaptive Goldilocks trial design alternative was developed.MethodsThe SHINE design includes response adaptive randomization, a sample size re-estimation, and monitoring for early efficacy and futility according to a group sequential design. The Goldilocks design includes more frequent monitoring for predicted success or futility and a longitudinal model of the primary endpoint. Both trial designs were simulated and compared in terms of their mean sample size and power across a range of treatment effects and success rates for the control group.ResultsAs simulated, the SHINE design tends to have slightly higher power and the Goldilocks design has a lower mean sample size. Both designs were tuned to have approximately 80% power to detect a difference of 25% versus 32% between control and treatment, respectively. In this scenario, mean sample sizes are 1,114 and 979 for the SHINE and Goldilocks designs, respectively.ConclusionsTwo designs were brought forward, and both were evaluated, revised, and improved based on the input of all parties involved in the ADAPT-IT process. However, the SHINE investigators were tasked with choosing only a single design to implement and ultimately elected not to implement the Goldilocks design. The Goldilocks design will be retrospectively executed upon completion of SHINE to later compare the designs based on their use of patient resources, time, and conclusions in a real world setting.Trial registrationClinicalTrials.gov NCT01369069 June 2011.

Statistical graphics in AJG: save the ink for the information.

In addition to being more memorable than tables, graphics can also illustrate multiple dimensions and important relationships far better than tables. Edward Tufte says it best (6): “Modern data graphics can do much more than simply substitute for small statistical tables. At their best, graphics are instruments for reasoning about quantitative information. Often the most effective way to describe, explore, and summarize a set of numbers— even a very large set—is to look at pictures of those numbers. Furthermore, of all methods for analyzing and communicating statistical information, well-designed data graphics are usually the simplest and at the same time the most powerful.” In this paper I highlight some of the best plots published in AJG in the past year, show some graphics that could be improved, and illustrate how perhaps one plot could convey information more directly than a table. Statistical Graphics in AJG: Save the Ink for the Information

Inhaled steroids reduce pain and sVCAM levels in individuals with sickle cell disease: A triple‐blind, randomized trial

Clinical and preclinical data demonstrate that altered pulmonary physiology (including increased inflammation, increased blood flow, airway resistance, and hyper‐reactivity) is an intrinsic component of Sickle Cell Disease (SCD) and may contribute to excess SCD morbidity and mortality. Inhaled corticosteroids (ICS), a safe and effective therapy for pulmonary inflammation in asthma, may ameliorate the altered pulmonary physiologic milieu in SCD. With this single‐center, longitudinal, randomized, triple‐blind, placebo controlled trial we studied the efficacy and feasibility of ICS in 54 nonasthmatic individuals with SCD. Participants received once daily mometasone furoate 220 mcg dry powder inhalation or placebo for 16 weeks. The primary outcome was feasibility (the number who complete the trial divided by the total number enrolled) with prespecified efficacy outcomes including daily pain score over time (patient reported) and change in soluble vascular cell adhesion molecule (sVCAM) levels between entry and 8‐weeks. For the primary outcome of feasibility, the result was 96% (52 of 54, 95% CI 87%‐99%) for the intent‐to‐treat analysis and 83% (45 of 54, 95% CI 71%‐91%) for the per‐protocol analysis. The adjusted treatment effect of mometasone was a reduction in daily pain score of 1.42 points (95%CI 0.61‐2.21, P = 0.001). Mometasone was associated with a reduction in sVCAM levels of 526.94 ng/mL more than placebo (95% CI 50.66‐1003.23, P = 0.03). These results support further study of ICS in SCD including multicenter trials and longer durations of treatment. www.clinicaltrials.gov (NCT02061202)

High-resolution transrectal ultrasound: pilot study of a novel technique for imaging clinically localized prostate cancer.

OBJECTIVES To determine how high-resolution transrectal ultrasound (HiTRUS) compares with conventional TRUS (LoTRUS) for the visualization of prostate cancer. METHODS AND MATERIALS Twenty-five men with known prostate cancer scheduled for radical prostatectomy were preoperatively imaged with both LoTRUS (5MHz) and HiTRUS (21MHz). Dynamic cine loops and still images for each modality were saved and subjected to blinded review by a radiologist looking for hypoechoic foci ≥ 5 mm in each sextant of the prostate. Following prostatectomy, areas of prostate cancer ≥ 5 mm on pathologic review were anatomically correlated to LoTRUS and HiTRUS findings. The accuracy of LoTRUS and HiTRUS to visualize prostate cancer in each sextant of the prostate and to identify high-grade and locally advanced disease was assessed. The McNemar test was used to compare sensitivity and specificity and paired dichotomous outcomes between imaging modalities. RESULTS Among 69 sextants with pathologically identified cancerous foci at radical prostatecomy, HiTRUS visualized 45 and missed 24, whereas LoTRUS visualized 26 and missed 43. Compared with LoTRUS, HiTRUS demonstrated improved sensitivity (65.2% vs. 37.7%) and specificity (71.6% vs. 65.4%). HiTRUSs agreement with pathologic findings was twice as high as LoTRUS (P = 0.006). HiTRUS provided a nonsignificant increase in visualization of high-grade lesions (84% vs. 60%, P = 0.11). CONCLUSIONS HiTRUS appears promising for prostate cancer imaging. Our initial experience suggests superiority to LoTRUS for the visualization of cancerous foci, and supports proceeding with a clinical trial in the biopsy setting.